Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3072 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0160. Min Range: -6.0160
Max Act: 6.0160. Min Act: -0.1700
Data Index: 2888911 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.9847. Min Act: -0.1700
Data Index: 5087563 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.8285. Min Act: -0.1700
Data Index: 7921006 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.7660. Min Act: -0.1700
Data Index: 7103184 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.7035. Min Act: -0.1700
Data Index: 1943918 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.7035. Min Act: -0.1700
Data Index: 3862690 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.6097. Min Act: -0.1700
Data Index: 4314076 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.5785. Min Act: -0.1700
Data Index: 3027798 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.4847. Min Act: -0.1700
Data Index: 870320 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.4847. Min Act: -0.1700
Data Index: 3861083 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.4535. Min Act: -0.1700
Data Index: 7864009 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.4535. Min Act: -0.1700
Data Index: 7110605 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.4535. Min Act: -0.1700
Data Index: 1925388 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.4222. Min Act: -0.1700
Data Index: 3226492 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.4222. Min Act: -0.1700
Data Index: 3098121 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.4222. Min Act: -0.1700
Data Index: 7839511 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.3910. Min Act: -0.1700
Data Index: 4551830 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.3910. Min Act: -0.1700
Data Index: 1776055 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.3910. Min Act: -0.1700
Data Index: 3869582 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0160. Min Range: -6.0160
Max Act: 5.3597. Min Act: -0.1700
Data Index: 7738829 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19